Re: [PATCH 04/15] dax: Introduce IOMAP_F_COW for copy-on-write

["Darrick J. Wong" <darrick.wong@oracle.com>]

On Tue, Mar 26, 2019 at 02:02:50PM -0500, Goldwyn Rodrigues wrote:
> From: Goldwyn Rodrigues <rgoldwyn@suse.com>
> 
> The IOMAP_F_COW is a flag to notify dax that it needs to copy
> the data from iomap->cow_addr to iomap->addr, if the start/end
> of I/O are not page aligned.
> 
> This also introduces dax_to_dax_copy() which performs a copy
> from one part of the device to another, to a maximum of one page.
> 
> Question: Using iomap.cow_addr == 0 means the CoW is to be copied
> (or memset) from a hole. Would this be better handled through a flag?
> 
> Signed-off-by: Goldwyn Rodrigues <rgoldwyn@suse.com>
> ---
>  fs/dax.c              | 36 ++++++++++++++++++++++++++++++++++++
>  include/linux/iomap.h |  3 +++
>  2 files changed, 39 insertions(+)
> 
> diff --git a/fs/dax.c b/fs/dax.c
> index ca0671d55aa6..e254535dd830 100644
> --- a/fs/dax.c
> +++ b/fs/dax.c
> @@ -1051,6 +1051,28 @@ static bool dax_range_is_aligned(struct block_device *bdev,
>  	return true;
>  }
>  
> +static void dax_to_dax_copy(struct iomap *iomap, loff_t pos, void *daddr,
> +			    size_t len)
> +{
> +	loff_t blk_start, blk_pg;
> +	void *saddr;
> +	ssize_t map_len;
> +
> +	/* A zero address is a hole. */
> +	if (iomap->cow_addr == 0) {
> +		memset(daddr, 0, len);
> +		return;
> +	}
> +
> +	blk_start = iomap->cow_addr + pos - iomap->cow_pos;
> +	blk_pg = round_down(blk_start, PAGE_SIZE);
> +
> +	map_len = dax_direct_access(iomap->dax_dev, PHYS_PFN(blk_pg), PAGE_SIZE,
> +			&saddr, NULL);
> +	saddr += blk_start - blk_pg;
> +	memcpy(daddr, saddr, len);
> +}
> +
>  int __dax_zero_page_range(struct block_device *bdev,
>  		struct dax_device *dax_dev, sector_t sector,
>  		unsigned int offset, unsigned int size)
> @@ -1143,6 +1165,20 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
>  			break;
>  		}
>  
> +		if (iomap->flags & IOMAP_F_COW) {
> +			loff_t pg_end = round_up(end, PAGE_SIZE);
> +			/*
> +			 * Copy the first part of the page
> +			 * Note: we pass offset as length
> +			 */
> +			if (offset)
> +				dax_to_dax_copy(iomap, pos - offset, kaddr, offset);
> +
> +			/* Copy the last part of the range */
> +			if (end < pg_end)
> +				dax_to_dax_copy(iomap, end, kaddr + offset + length, pg_end - end);
> +		}
> +
>  		map_len = PFN_PHYS(map_len);
>  		kaddr += offset;
>  		map_len -= offset;
> diff --git a/include/linux/iomap.h b/include/linux/iomap.h
> index 0fefb5455bda..391785de1428 100644
> --- a/include/linux/iomap.h
> +++ b/include/linux/iomap.h

Probably a good idea to cc the iomap maintainers on this (entire
patchset)... <cough>

--D

> @@ -35,6 +35,7 @@ struct vm_fault;
>  #define IOMAP_F_NEW		0x01	/* blocks have been newly allocated */
>  #define IOMAP_F_DIRTY		0x02	/* uncommitted metadata */
>  #define IOMAP_F_BUFFER_HEAD	0x04	/* file system requires buffer heads */
> +#define IOMAP_F_COW		0x08	/* cow before write */
>  
>  /*
>   * Flags that only need to be reported for IOMAP_REPORT requests:
> @@ -59,6 +60,8 @@ struct iomap {
>  	u64			length;	/* length of mapping, bytes */
>  	u16			type;	/* type of mapping */
>  	u16			flags;	/* flags for mapping */
> +	u64			cow_addr; /* read address to perform CoW */
> +	loff_t			cow_pos; /* file offset of cow_addr */
>  	struct block_device	*bdev;	/* block device for I/O */
>  	struct dax_device	*dax_dev; /* dax_dev for dax operations */
>  	void			*inline_data;
> -- 
> 2.16.4
>